List your company
ResearchFormerly WizWand

Chinese Knowledge on CEval

82.16AccuracyQwen3.5-9B
8.777627.828846.8865.9312Jul 23, 2024Nov 10, 2024Feb 28, 2025Jun 18, 2025Oct 6, 2025Jan 24, 2026May 14, 2026
Updated 5mo ago

Evaluation results

MethodLinks
Qwen3.5-9BShots=52026.0482.16
Qwen3-14BShots=52026.0481.78
Qwen3-8BShots=52026.0478.59
XekRung-8BShots=52026.0476.65
Qwen-1.5 7BRole=Teacher2024.0774.1
Llama-3.3-70B-InstructShots=52026.0469.96
SecGPT-14BShots=52026.0467.51
DDKBase Model=Qwen-1.5 1.8B, Teacher=Qwen-1.5 7B2024.0764.41
KDBase Model=Qwen-1.5 1.8B, Teacher=Qwen-1.5 7B2024.0762.63
MiniLLMBase Model=Qwen-1.5 1.8B, Teacher=Qwen-1.5 7B2024.0762.4
CPTBase Model=Qwen-1.5 1.8B, Teacher=Qwen-1.5 7B2024.0760.13
Qwen-1.5 1.8BRole=Student2024.0759.66
AdaMoESparsity Level=Mid Sparsity, Null=64, Avg. K=3.252026.0557.28
BEAMSparsity Level=High Sparsity, beta=0.1, Avg. K=1.082026.0556.15
Top-K ReducedSparsity Level=Mid Sparsity, K=4, Avg. K=4.002026.0555.89
DeepSeekV2-LiteK=6, Avg. K=6.002026.0555.26
MoE-DynamicSparsity Level=High Sparsity, phi=0.1, Avg. K=3.902026.0555.1
AdaMoESparsity Level=High Sparsity, Null=128, Avg. K=2.112026.0554.83
BEAMSparsity Level=Mid Sparsity, beta=0.01, Avg. K=2.612026.0554.12
MoE-DynamicSparsity Level=Mid Sparsity, phi=0.3, Avg. K=4.312026.0553.36
Top-K ReducedSparsity Level=High Sparsity, K=2, Avg. K=2.002026.0553.35
Top-K PruningSparsity Level=Mid Sparsity, K=4, Avg. K=4.002026.0553.25
Top-K PruningSparsity Level=High Sparsity, K=2, Avg. K=2.002026.0551.06
BEAMSparsity Level=Extreme Sparsity, beta=1.0, Avg. K=0.482026.0550.11
Top-K ReducedSparsity Level=Extreme Sparsity, K=1, Avg. K=1.002026.0541.46
Llama-Primus-Reasoning-8BShots=52026.0436.8
Llama-3.1-8B-InstructShots=52026.0431.3
Foundation-Sec-8B-ReasoningShots=52026.0411.6